@inproceedings{popovic-castilho-2019-challenge,
title = "Challenge Test Sets for {MT} Evaluation",
author = "Popovi{\'c}, Maja and
Castilho, Sheila",
editor = "Rossi, Laura",
booktitle = "Proceedings of Machine Translation Summit XVII: Tutorial Abstracts",
month = aug,
year = "2019",
address = "Dublin, Ireland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/W19-7602",
abstract = "Most of the test sets used for the evaluation of MT systems reflect the frequency distribution of different phenomena found in naturally occurring data ({''}standard{''} or {''}natural{''} test sets). However, to better understand particular strengths and weaknesses of MT systems, especially those based on neural networks, it is necessary to apply more focused evaluation procedures. Therefore, another type of test sets ({''}challenge{''} test sets, also called {''}test suites{''}) is being increasingly employed in order to highlight points of difficulty which are relevant to model development, training, or using of the given system. This tutorial will be useful for anyone (researchers, developers, users, translators) interested in detailed evaluation and getting a better understanding of machine translation (MT) systems and models. The attendees will learn about the motivation and linguistic background of challenge test sets and a range of testing possibilities applied to the state-of-the-art MT systems, as well as a number of practical aspects and challenges.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popovic-castilho-2019-challenge">
<titleInfo>
<title>Challenge Test Sets for MT Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheila</namePart>
<namePart type="family">Castilho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XVII: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most of the test sets used for the evaluation of MT systems reflect the frequency distribution of different phenomena found in naturally occurring data (”standard” or ”natural” test sets). However, to better understand particular strengths and weaknesses of MT systems, especially those based on neural networks, it is necessary to apply more focused evaluation procedures. Therefore, another type of test sets (”challenge” test sets, also called ”test suites”) is being increasingly employed in order to highlight points of difficulty which are relevant to model development, training, or using of the given system. This tutorial will be useful for anyone (researchers, developers, users, translators) interested in detailed evaluation and getting a better understanding of machine translation (MT) systems and models. The attendees will learn about the motivation and linguistic background of challenge test sets and a range of testing possibilities applied to the state-of-the-art MT systems, as well as a number of practical aspects and challenges.</abstract>
<identifier type="citekey">popovic-castilho-2019-challenge</identifier>
<location>
<url>https://aclanthology.org/W19-7602</url>
</location>
<part>
<date>2019-08</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Challenge Test Sets for MT Evaluation
%A Popović, Maja
%A Castilho, Sheila
%Y Rossi, Laura
%S Proceedings of Machine Translation Summit XVII: Tutorial Abstracts
%D 2019
%8 August
%I European Association for Machine Translation
%C Dublin, Ireland
%F popovic-castilho-2019-challenge
%X Most of the test sets used for the evaluation of MT systems reflect the frequency distribution of different phenomena found in naturally occurring data (”standard” or ”natural” test sets). However, to better understand particular strengths and weaknesses of MT systems, especially those based on neural networks, it is necessary to apply more focused evaluation procedures. Therefore, another type of test sets (”challenge” test sets, also called ”test suites”) is being increasingly employed in order to highlight points of difficulty which are relevant to model development, training, or using of the given system. This tutorial will be useful for anyone (researchers, developers, users, translators) interested in detailed evaluation and getting a better understanding of machine translation (MT) systems and models. The attendees will learn about the motivation and linguistic background of challenge test sets and a range of testing possibilities applied to the state-of-the-art MT systems, as well as a number of practical aspects and challenges.
%U https://aclanthology.org/W19-7602
Markdown (Informal)
[Challenge Test Sets for MT Evaluation](https://aclanthology.org/W19-7602) (Popović & Castilho, MTSummit 2019)
ACL
- Maja Popović and Sheila Castilho. 2019. Challenge Test Sets for MT Evaluation. In Proceedings of Machine Translation Summit XVII: Tutorial Abstracts, Dublin, Ireland. European Association for Machine Translation.